Title :
Positions research of agriculture vehicle navigation system based on Radial Basis Function neural network and Particle Swarm Optimization
Author :
Ji, Ying ; Zhang, Man ; Liu, Gang ; Liu, Zhanxiang
Abstract :
Kalman filter is used commonly in agriculture vehicle navigation, but it is limited in linear system and has special request on noises. In practice, it is difficult to meet all the requests. To avoid the disadvantage of kalman filter, the RBF neural network is used to fuse the multi-sensor information to get the position information; Particle Swarm Optimization theory is introduced to the learning RBF neural network training process. The best neural network structure can be found by using particle swarm optimization algorithm to optimize the parameters of the RBF neural network. Experiment results indicate that RBF algorithm is better than the kalman filter, which can obtain more precise and more robust position information.
Keywords :
Kalman filters; agriculture; computerised navigation; particle swarm optimisation; radial basis function networks; sensor fusion; Kalman filter; agriculture vehicle navigation system; multisensor information; particle swarm optimization; position information; radial basis function neural network; Agriculture; Artificial neural networks; Kalman filters; Navigation; Particle swarm optimization; Training; Vehicles; Particle swarm optimization; fusion algorithm; neural network; position;
Conference_Titel :
Natural Computation (ICNC), 2010 Sixth International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5958-2
DOI :
10.1109/ICNC.2010.5583145